Joe Dong | Physical AI Deep Dives
Subscribe
Sign in
Home
Notes
Essays
Archive
About
Data Gloves Should Be Rigid
Why better robot training data starts with rigid surfaces and moving joints.
Sep 11
•
Joe Dong
1
1
June 2026
The right hand is the one you can capture
In embodied AI, data sourcing is the first-order question. Follow it all the way down and it rewrites the model, the morphology — and what counts as a…
Jun 30
•
Joe Dong
1
May 2026
System Thinking and Model Thinking in Robot Learning
Both schools are betting on the same variable -- DATA.
May 11
•
Joe Dong
2
1
April 2026
Robot Learning Should Be Goal-Driven and Data-First
A goal-driven view on robot learning, industrial deployment, and the data engine needed to scale dexterous robots.
Apr 28
•
Joe Dong
1
1
π0.7: Prompt Engineering Comes to Robot Foundation Models
π0.7’s key advance is full action context, not just a stronger model—unlocking compositional generalization.
Apr 23
•
Joe Dong
3
1
NVIDIA EgoScale: Pretraining Dexterous Manipulation with 20,000 Hours of Egocentric Human Data
A simple but important idea: pretrain on large-scale human egocentric data first, then use a small amount of aligned human–robot data and robot…
Apr 14
•
Joe Dong
2
1
Nvidia DreamZero0: Why World Models May Become Policies
DreamZero0 is not just a stronger robotics benchmark.
Apr 8
•
Joe Dong
2
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
